genshin-assistant/scripts/analyze-native-review.ts

import fs from "node:fs/promises";
import os from "node:os";
import path from "node:path";
import { parseArtifactCandidate } from "../src/lib/artifactOcrParser.js";
import { artifactReviewReasons } from "../src/lib/scannerLearning.js";
import type { CaptureResult } from "../src/types/global.js";

type ProcessingOcrEntry = NonNullable<CaptureResult["ocr"]>[number];

type ProcessingResult = {
  sequence: number;
  page?: number;
  capturedAt?: string;
  parsed?: boolean;
  needsReview?: boolean;
  artifactName?: string;
  slot?: string;
  setName?: string;
  ikMatch?: { matched?: boolean; notes?: string[] };
  notes?: string[];
  ocr?: ProcessingOcrEntry[];
};

type ProcessingReport = {
  results?: ProcessingResult[];
};

const options = parseArgs(process.argv.slice(2));
const scanRoot = path.join(
  process.env.APPDATA || path.join(os.homedir(), "AppData", "Roaming"),
  "genshin-artifact-assistant",
  "native-scans",
);
const runDir = options.runDir ? path.resolve(options.runDir) : await latestRunDir(scanRoot);
const sourcePath = path.join(runDir, "processing-report.json");
const source = JSON.parse(await fs.readFile(sourcePath, "utf8")) as ProcessingReport;
const sourceResults = Array.isArray(source.results) ? source.results : [];
if (sourceResults.length === 0) throw new Error(`No processing results found in ${sourcePath}`);

const analyzed = sourceResults.map((sourceResult) => {
  const parsed = parseArtifactCandidate(captureFromProcessingResult(sourceResult));
  const reasons = artifactReviewReasons(parsed);
  if (sourceResult.ikMatch && !sourceResult.ikMatch.matched) reasons.push("ik_mismatch");
  const uniqueReasons = [...new Set(reasons)];
  const needsReview = uniqueReasons.length > 0;
  const oldNeedsReview = Boolean(sourceResult.needsReview);
  const repairedInitialMainValue = Boolean(
    parsed
    && parsed.level === 0
    && parsed.substats.length === 4
    && parsed.fields.mainValue.source === "derived"
    && parsed.fields.mainValue.confidence >= 90
    && sourceResult.notes?.some((note) => /mainValue confidence is low/i.test(note)),
  );
  return {
    sequence: sourceResult.sequence,
    page: sourceResult.page ?? 0,
    oldNeedsReview,
    needsReview,
    reasons: uniqueReasons,
    level: parsed?.level ?? null,
    artifactName: parsed?.name ?? "Unknown artifact",
    slot: parsed?.slot ?? "Unknown slot",
    mainStat: parsed?.mainStat ?? "Unknown main stat",
    mainValue: parsed?.mainValue ?? "?",
    substatCount: parsed?.substats.length ?? 0,
    extractionConfidence: parsed?.confidence ?? 0,
    repairedInitialMainValue,
  };
});

const review = analyzed.filter((entry) => entry.needsReview);
const report = {
  version: "native-review-analysis-v1",
  createdAt: new Date().toISOString(),
  runId: path.basename(runDir),
  runDir,
  sourcePath,
  total: analyzed.length,
  parsed: analyzed.filter((entry) => entry.artifactName !== "Unknown artifact").length,
  oldReview: analyzed.filter((entry) => entry.oldNeedsReview).length,
  review: review.length,
  reviewRate: review.length / analyzed.length,
  reclassifiedToClean: analyzed.filter((entry) => entry.oldNeedsReview && !entry.needsReview).length,
  reclassifiedToReview: analyzed.filter((entry) => !entry.oldNeedsReview && entry.needsReview).length,
  repairedInitialMainValues: analyzed.filter((entry) => entry.repairedInitialMainValue).length,
  reasons: groupStrings(review.flatMap((entry) => entry.reasons)),
  levels: groupStrings(review.map((entry) => String(entry.level ?? "missing"))),
  pageBands: groupStrings(review.map((entry) => pageBand(entry.page))),
  remainingSamples: review.slice(0, 25),
};

const outputDir = options.outputDir
  ? path.resolve(options.outputDir)
  : path.resolve("outputs", "native-review-analysis", report.runId);
await fs.mkdir(outputDir, { recursive: true });
const reportPath = path.join(outputDir, "native-review-analysis.json");
await fs.writeFile(reportPath, JSON.stringify(report, null, 2), "utf8");

console.log(`Native review analysis: ${report.runId}`);
console.log(`Results: ${report.total}; old review=${report.oldReview}; current review=${report.review} (${(report.reviewRate * 100).toFixed(2)}%)`);
console.log(`Reclassified: clean=${report.reclassifiedToClean}; review=${report.reclassifiedToReview}; initial-main repairs=${report.repairedInitialMainValues}`);
console.log(`Top reasons: ${report.reasons.slice(0, 8).map((entry) => `${entry.name}=${entry.count}`).join(", ") || "none"}`);
console.log(`Report: ${reportPath}`);

if (options.maxReviewRate !== null && report.reviewRate > options.maxReviewRate) {
  throw new Error(`Review rate ${(report.reviewRate * 100).toFixed(2)}% exceeds ${(options.maxReviewRate * 100).toFixed(2)}%.`);
}

function captureFromProcessingResult(result: ProcessingResult): CaptureResult {
  return {
    id: `native-review-${result.sequence}`,
    name: result.artifactName || `native-review-${result.sequence}`,
    width: 492,
    height: 838,
    dataUrl: "",
    capturedAt: result.capturedAt || new Date(0).toISOString(),
    captureTarget: "genshin-client",
    ocr: Array.isArray(result.ocr) ? result.ocr : [],
  };
}

function groupStrings(values: string[]) {
  const counts = new Map<string, number>();
  for (const value of values) counts.set(value, (counts.get(value) ?? 0) + 1);
  return [...counts.entries()]
    .map(([name, count]) => ({ name, count }))
    .sort((left, right) => right.count - left.count || left.name.localeCompare(right.name));
}

function pageBand(page: number) {
  if (!Number.isFinite(page) || page < 1) return "missing";
  const start = Math.floor((page - 1) / 5) * 5 + 1;
  return `${String(start).padStart(2, "0")}-${String(start + 4).padStart(2, "0")}`;
}

function parseArgs(args: string[]) {
  const runDir = valueArg(args, "--run-dir=");
  const outputDir = valueArg(args, "--output-dir=");
  const rawMaximum = valueArg(args, "--max-review-rate=");
  const parsedMaximum = rawMaximum ? Number(rawMaximum) : Number.NaN;
  const maxReviewRate = Number.isFinite(parsedMaximum)
    ? Math.max(0, Math.min(1, parsedMaximum))
    : null;
  return { runDir, outputDir, maxReviewRate };
}

function valueArg(args: string[], prefix: string) {
  return args.find((argument) => argument.startsWith(prefix))?.slice(prefix.length) ?? "";
}

async function latestRunDir(root: string) {
  const entries = await fs.readdir(root, { withFileTypes: true });
  const candidates = entries.filter((entry) => entry.isDirectory()).map((entry) => entry.name).sort().reverse();
  for (const candidate of candidates) {
    const runDir = path.join(root, candidate);
    try {
      await fs.access(path.join(runDir, "processing-report.json"));
      return runDir;
    } catch {
      // Continue; this is a read-only saved-run analysis.
    }
  }
  throw new Error(`No processing-report.json found below ${root}`);
}